[llvm] AMDGPU/GlobalISel: Handle inreg arguments as SGPRs (PR #78123)
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Sun Jan 14 20:31:04 PST 2024
https://github.com/arsenm created https://github.com/llvm/llvm-project/pull/78123
This is the missing GISel part of 54470176afe20b16e6b026ab989591d1d19ad2b7
>From 717028b030681b2479ac3af4bcfcb7ecdcc5a4b4 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Sat, 13 Jan 2024 09:54:24 +0700
Subject: [PATCH] AMDGPU/GlobalISel: Handle inreg arguments as SGPRs
This is the missing GISel part of 54470176afe20b16e6b026ab989591d1d19ad2b7
---
llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp | 4 -
.../AMDGPU/GlobalISel/irtranslator-call.ll | 791 ++++++++++++++++++
.../GlobalISel/irtranslator-function-args.ll | 458 ++++++++++
3 files changed, 1249 insertions(+), 4 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
index cf2896f80f19bb..7d98c841647540 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
@@ -632,10 +632,6 @@ bool AMDGPUCallLowering::lowerFormalArguments(
const bool InReg = Arg.hasAttribute(Attribute::InReg);
- // SGPR arguments to functions not implemented.
- if (!IsGraphics && InReg)
- return false;
-
if (Arg.hasAttribute(Attribute::SwiftSelf) ||
Arg.hasAttribute(Attribute::SwiftError) ||
Arg.hasAttribute(Attribute::Nest))
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll
index e29d1781d3dff3..b41ecbbb07f2a9 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll
@@ -87,6 +87,24 @@ declare hidden void @external_void_func_12xv3f32(<3 x float>, <3 x float>, <3 x
declare hidden void @external_void_func_8xv5f32(<5 x float>, <5 x float>, <5 x float>, <5 x float>,
<5 x float>, <5 x float>, <5 x float>, <5 x float>) #0
+declare hidden void @external_void_func_i16_inreg(i32 inreg) #0
+declare hidden void @external_void_func_i32_inreg(i32 inreg) #0
+declare hidden void @external_void_func_i64_inreg(i64 inreg) #0
+declare hidden void @external_void_func_v2i32_inreg(<2 x i32> inreg) #0
+declare hidden void @external_void_func_f16_inreg(half inreg) #0
+declare hidden void @external_void_func_bf16_inreg(bfloat inreg) #0
+declare hidden void @external_void_func_f32_inreg(float inreg) #0
+declare hidden void @external_void_func_f64_inreg(double inreg) #0
+declare hidden void @external_void_func_v2f16_inreg(<2 x half> inreg) #0
+declare hidden void @external_void_func_v3f16_inreg(<3 x half> inreg) #0
+declare hidden void @external_void_func_v4f16_inreg(<4 x half> inreg) #0
+
+declare hidden void @external_void_func_p0_inreg(ptr inreg) #0
+declare hidden void @external_void_func_p1_inreg(ptr addrspace(1) inreg) #0
+declare hidden void @external_void_func_p3_inreg(ptr addrspace(3) inreg) #0
+declare hidden void @external_void_func_v2p1_inreg(<2 x ptr addrspace(1)> inreg) #0
+declare hidden void @external_void_func_v2p5_inreg(<2 x ptr addrspace(5)> inreg) #0
+
; amdgpu_gfx calling convention
declare hidden amdgpu_gfx void @external_gfx_void_func_void() #0
declare hidden amdgpu_gfx void @external_gfx_void_func_i32(i32) #0
@@ -5263,6 +5281,779 @@ main_body:
ret void
}
+define void @test_call_external_void_func_i16_inreg(i16 inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_i16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY9]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_i16_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; CHECK-NEXT: $sgpr0 = COPY [[ANYEXT]](s32)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_i16_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_i16_inreg(i16 inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_i32_inreg(i32 inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_i32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_i32_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: $sgpr0 = COPY [[COPY9]](s32)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_i32_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_i32_inreg(i32 inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_i64_inreg(i64 inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_i64_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY9]](s32), [[COPY10]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_i64_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[MV]](s64)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_i64_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_i64_inreg(i64 inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_v2i32_inreg(<2 x i32> inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_v2i32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY9]](s32), [[COPY10]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_v2i32_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<2 x s32>)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_v2i32_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_v2i32_inreg(<2 x i32> inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_f16_inreg(half inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_f16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY9]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_f16_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; CHECK-NEXT: $sgpr0 = COPY [[ANYEXT]](s32)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_f16_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_f16_inreg(half inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_bf16_inreg(bfloat inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_bf16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY9]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_bf16_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; CHECK-NEXT: $sgpr0 = COPY [[ANYEXT]](s32)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_bf16_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_bf16_inreg(bfloat inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_f32_inreg(float inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_f32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_f32_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: $sgpr0 = COPY [[COPY9]](s32)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_f32_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_f32_inreg(float inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_f64_inreg(double inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_f64_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY9]](s32), [[COPY10]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_f64_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[MV]](s64)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_f64_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_f64_inreg(double inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_v2f16_inreg(<2 x half> inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_v2f16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr0
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_v2f16_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: $sgpr0 = COPY [[COPY9]](<2 x s16>)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_v2f16_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_v2f16_inreg(<2 x half> inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_v3f16_inreg(<3 x half> inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_v3f16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr1
+ ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY9]](<2 x s16>), [[COPY10]](<2 x s16>)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s16>)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s16>) = G_BUILD_VECTOR [[UV]](s16), [[UV1]](s16), [[UV2]](s16)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_v3f16_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16), [[UV6:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s16>)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[UV4]](s16), [[UV5]](s16), [[UV6]](s16), [[DEF]](s16)
+ ; CHECK-NEXT: [[UV7:%[0-9]+]]:_(<2 x s16>), [[UV8:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[BUILD_VECTOR1]](<4 x s16>)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV7]](<2 x s16>)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV8]](<2 x s16>)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_v3f16_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_v3f16_inreg(<3 x half> inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_v4f16_inreg(<4 x half> inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_v4f16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr1
+ ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY9]](<2 x s16>), [[COPY10]](<2 x s16>)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_v4f16_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s16>)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](<2 x s16>)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](<2 x s16>)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_v4f16_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_v4f16_inreg(<4 x half> inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_p0_inreg(ptr inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_p0_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY9]](s32), [[COPY10]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_p0_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[MV]](p0)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_p0_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_p0_inreg(ptr inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_p1_inreg(ptr addrspace(1) inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_p1_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY9]](s32), [[COPY10]](s32)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_p1_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[MV]](p1)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_p1_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_p1_inreg(ptr addrspace(1) inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_p3_inreg(ptr addrspace(3) inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_p3_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p3) = COPY $sgpr0
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_p3_inreg
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: $sgpr0 = COPY [[COPY9]](p3)
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY19]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY13]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY14]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_p3_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_p3_inreg(ptr addrspace(3) inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_v2p1_inreg(<2 x ptr addrspace(1)> inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_v2p1_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(s32) = COPY $sgpr3
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY9]](s32), [[COPY10]](s32)
+ ; CHECK-NEXT: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY11]](s32), [[COPY12]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_v2p1_inreg
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<2 x p1>)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: $sgpr2 = COPY [[UV2]](s32)
+ ; CHECK-NEXT: $sgpr3 = COPY [[UV3]](s32)
+ ; CHECK-NEXT: [[COPY22:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY22]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY14]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY15]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY16]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY20]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY21]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_v2p1_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $sgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_v2p1_inreg(<2 x ptr addrspace(1)> inreg %arg)
+ ret void
+}
+
+define void @test_call_external_void_func_v2p5_inreg(<2 x ptr addrspace(5)> inreg %arg) #0 {
+ ; CHECK-LABEL: name: test_call_external_void_func_v2p5_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr31, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr31
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p5) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p5) = COPY $sgpr1
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p5>) = G_BUILD_VECTOR [[COPY9]](p5), [[COPY10]](p5)
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
+ ; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @external_void_func_v2p5_inreg
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY8]]
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(p4) = COPY [[COPY6]]
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(s64) = COPY [[COPY5]]
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:_(s32) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:_(s32) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY19:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<2 x p5>)
+ ; CHECK-NEXT: $sgpr0 = COPY [[UV]](s32)
+ ; CHECK-NEXT: $sgpr1 = COPY [[UV1]](s32)
+ ; CHECK-NEXT: [[COPY20:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY20]](<4 x s32>)
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY11]](p4)
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY12]](p4)
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY13]](p4)
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY14]](s64)
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY15]](s32)
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32)
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32)
+ ; CHECK-NEXT: $sgpr15 = COPY [[COPY18]](s32)
+ ; CHECK-NEXT: $vgpr31 = COPY [[COPY19]](s32)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent G_SI_CALL [[GV]](p0), @external_void_func_v2p5_inreg, csr_amdgpu, implicit $sgpr0, implicit $sgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc
+ ; CHECK-NEXT: SI_RETURN
+ call void @external_void_func_v2p5_inreg(<2 x ptr addrspace(5)> inreg %arg)
+ ret void
+}
+
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
attributes #2 = { nounwind noinline }
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll
index 062d2e173e6d8a..04fff32ab84aa9 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll
@@ -2777,4 +2777,462 @@ define void @vector_ptr_in_struct_arg({ <2 x ptr addrspace(1)>, <2 x ptr addrspa
ret void
}
+define void @void_func_i1_inreg(i1 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i1_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC]](s1), [[DEF]](p1) :: (store (s1) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i1 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i8_inreg(i8 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i8_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC]](s16)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC1]](s8), [[DEF]](p1) :: (store (s8) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i8 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i16_inreg(i16 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC]](s16), [[DEF]](p1) :: (store (s16) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i16 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i32_inreg(i32 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[COPY]](s32), [[DEF]](p1) :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i32 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i48_inreg(i48 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i48_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s48) = G_TRUNC [[MV]](s64)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC]](s48), [[DEF]](p1) :: (store (s48) into `ptr addrspace(1) undef`, align 8, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i48 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i64_inreg(i64 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i64_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](s64), [[DEF]](p1) :: (store (s64) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i64 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i96_inreg(i96 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i96_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s96) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](s96), [[DEF]](p1) :: (store (s96) into `ptr addrspace(1) undef`, align 8, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i96 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_i128_inreg(i128 inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_i128_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr3
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](s128), [[DEF]](p1) :: (store (s128) into `ptr addrspace(1) undef`, align 8, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store i128 %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_f16_inreg(half inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_f16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC]](s16), [[DEF]](p1) :: (store (s16) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store half %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_bf16_inreg(bfloat inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_bf16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC]](s16), [[DEF]](p1) :: (store (s16) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store bfloat %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_f32_inreg(float inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_f32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[COPY]](s32), [[DEF]](p1) :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store float %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_f64_inreg(double inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_f64_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](s64), [[DEF]](p1) :: (store (s64) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store double %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2i1_inreg(<2 x i1> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2i1_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
+ ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(<2 x s1>) = G_TRUNC [[BUILD_VECTOR]](<2 x s16>)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC2]](<2 x s1>), [[DEF]](p1) :: (store (<2 x s1>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x i1> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+
+define void @void_func_v2i8_inreg(<2 x i8> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2i8_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
+ ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(<2 x s8>) = G_TRUNC [[BUILD_VECTOR]](<2 x s16>)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[TRUNC2]](<2 x s8>), [[DEF]](p1) :: (store (<2 x s8>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x i8> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2i16_inreg(<2 x i16> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2i16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr0
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[COPY]](<2 x s16>), [[DEF]](p1) :: (store (<2 x s16>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x i16> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2f16_inreg(<2 x half> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2f16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $sgpr0
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[COPY]](<2 x s16>), [[DEF]](p1) :: (store (<2 x s16>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x half> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2bf16_inreg(<2 x bfloat> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2bf16_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BITCAST]](<2 x s16>), [[DEF]](p1) :: (store (<2 x s16>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x bfloat> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2i32_inreg(<2 x i32> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2i32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x s32>), [[DEF]](p1) :: (store (<2 x s32>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x i32> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2f32_inreg(<2 x float> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2f32_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x s32>), [[DEF]](p1) :: (store (<2 x s32>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x float> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2i64_inreg(<2 x i64> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2i64_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr3
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV]](s64), [[MV1]](s64)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x s64>), [[DEF]](p1) :: (store (<2 x s64>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x i64> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2f64_inreg(<2 x double> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2f64_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr3
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV]](s64), [[MV1]](s64)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x s64>), [[DEF]](p1) :: (store (<2 x s64>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x double> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+; FIXME: Broken, see issue #78121
+; define void @void_func_v2i128_inreg(<2 x i128> inreg %arg0) #0 {
+; store <2 x i128> %arg0, ptr addrspace(1) undef
+; ret void
+; }
+
+; define void @void_func_v2f128_inreg(<2 x fp128> inreg %arg0) #0 {
+; store <2 x fp128> %arg0, ptr addrspace(1) undef
+; ret void
+; }
+
+define void @void_func_p0_inreg(ptr inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_p0_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](p0), [[DEF]](p1) :: (store (p0) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store ptr %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_p1_inreg(ptr addrspace(1) inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_p1_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](p1), [[DEF]](p1) :: (store (p1) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store ptr addrspace(1) %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_p3_inreg(ptr addrspace(3) inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_p3_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p3) = COPY $sgpr0
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[COPY]](p3), [[DEF]](p1) :: (store (p3) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store ptr addrspace(3) %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_p5_inreg(ptr addrspace(5) inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_p5_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p5) = COPY $sgpr0
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[COPY]](p5), [[DEF]](p1) :: (store (p5) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store ptr addrspace(5) %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_p999_inreg(ptr addrspace(999) inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_p999_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p999) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[MV]](p999), [[DEF]](p1) :: (store (p999) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store ptr addrspace(999) %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2p0_inreg(<2 x ptr> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2p0_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr3
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[MV1:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p0>) = G_BUILD_VECTOR [[MV]](p0), [[MV1]](p0)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x p0>), [[DEF]](p1) :: (store (<2 x p0>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x ptr> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2p1_inreg(<2 x ptr addrspace(1)> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2p1_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $sgpr3
+ ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+ ; CHECK-NEXT: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x p1>), [[DEF]](p1) :: (store (<2 x p1>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x ptr addrspace(1)> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
+define void @void_func_v2p3_inreg(<2 x ptr addrspace(3)> inreg %arg0) #0 {
+ ; CHECK-LABEL: name: void_func_v2p3_inreg
+ ; CHECK: bb.1 (%ir-block.0):
+ ; CHECK-NEXT: liveins: $sgpr0, $sgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p3) = COPY $sgpr0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(p3) = COPY $sgpr1
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p3>) = G_BUILD_VECTOR [[COPY]](p3), [[COPY1]](p3)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<2 x p3>), [[DEF]](p1) :: (store (<2 x p3>) into `ptr addrspace(1) undef`, addrspace 1)
+ ; CHECK-NEXT: SI_RETURN
+ store <2 x ptr addrspace(3)> %arg0, ptr addrspace(1) undef
+ ret void
+}
+
attributes #0 = { nounwind }
+
+
More information about the llvm-commits
mailing list